Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    discussions related to performance metrics and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Performance" followed by a preposition or noun

    np_acts-logits-general · gemini-2.0-flash

    performance measurement and reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.99
     Wikimedijinoj
    -0.77
     ligiloj
    -0.76
    RenderAtEndOf
    -0.74
     BoxFit
    -0.74
     ostavi
    -0.73
     kaynağından
    -0.68
    AsUp
    -0.68
     للمعارف
    -0.67
    SequentialGroup
    -0.66
    POSITIVE LOGITS
    Performances
    0.79
     performances
    0.74
     Performances
    0.73
     arts
    0.66
     PERFORM
    0.61
     Performing
    0.57
    +:+
    0.57
    ('-'
    0.57
     performers
    0.56
     Perform
    0.56
    Act Density 0.089%

    No Known Activations